Research on Semantic Segmentation of Natural Landform Based on Edge Detection Module

Authors

Qizong Shen, School of Mechanical Engineering, Hebei University of Technology, Tianjin 300130, China;Follow
Chunyan Gao, School of Mechanical Engineering, Hebei University of Technology, Tianjin 300130, China;

Abstract

Abstract: To classify pixels of natural landform edges in remote sensing images, this paper proposes a multi-channel fusion model and a decoder-side module model both integrating an edge detection module. The edge detection module takes the Canny operator as the base to perform closed operations and mean filtering, as a result of which accurate image edges can be achieved. Based on DeepLabV3+, the semantic segmentation network is connected with an edge planning module in parallel at encoder and decoder sides respectively. The experimental results show that the two improved networks can achieve a better segmentation effect on a high-resolution natural landform image data set compared with the original DeepLabV3+ network. Particularly, the network with fusion at the decoder side achieves the highest intersection over union (IoU) of 72.60% and F1score of 86.64%, which can be used for the recognition and segmentation of natural landforms.

Recommended Citation

Shen, Qizong and Gao, Chunyan (2022) "Research on Semantic Segmentation of Natural Landform Based on Edge Detection Module," Journal of System Simulation: Vol. 34: Iss. 2, Article 12.
DOI: 10.16182/j.issn1004731x.joss.20-0756
Available at: https://dc-china-simulation.researchcommons.org/journal/vol34/iss2/12

First Page

293

Revised Date

2020-11-22

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.20-0756

Last Page

302

CLC

TP391

Recommended Citation

Qizong Shen, Chunyan Gao. Research on Semantic Segmentation of Natural Landform Based on Edge Detection Module[J]. Journal of System Simulation, 2022, 34(2): 293-302.

DOI

10.16182/j.issn1004731x.joss.20-0756